Stochastic Augmented-Based Dual-Teaching for Semi-Supervised Medical Image Segmentation

作     者：Hengyang Liu Yang Yuan Pengcheng Ren Chengyun Song Fen Luo 

作者机构：School of Computer Science and EngineeringChongqing University of TechnologyChongqing400054China College of Artificial IntelligenceChongqing Technology and Business UniversityChongqing400067China 

出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)

年 卷 期：2025年第82卷第1期

页      面：543-560页

核心收录：

学科分类：08[工学] 080203[工学-机械设计及理论] 0802[工学-机械工程] 

基　　金：supported by the Natural Science Foundation of China(No.41804112 author:Chengyun Song) 

主　　题：Semi-supervised medical image segmentation contrastive learning stochastic augmented 

摘      要：Existing semi-supervisedmedical image segmentation algorithms use copy-paste data augmentation to correct the labeled-unlabeled data distribution ***,current copy-paste methods have three limitations:(1)training the model solely with copy-paste mixed pictures from labeled and unlabeled input loses a lot of labeled information;(2)low-quality pseudo-labels can cause confirmation bias in pseudo-supervised learning on unlabeled data;(3)the segmentation performance in low-contrast and local regions is less than *** design a Stochastic Augmentation-Based Dual-Teaching Auxiliary Training Strategy(SADT),which enhances feature diversity and learns high-quality features to overcome these *** be more precise,SADT trains the Student Network by using pseudo-label-based training from Teacher Network 1 and supervised learning with labeled data,which prevents the loss of rare labeled *** introduce a bi-directional copy-pastemask with progressive high-entropy filtering to reduce data distribution disparities and mitigate confirmation bias in *** the mixed images,Deep-Shallow Spatial Contrastive Learning(DSSCL)is proposed in the feature spaces of Teacher Network 2 and the Student Network to improve the segmentation capabilities in low-contrast and local *** this procedure,the features retrieved by the Student Network are subjected to a random feature perturbation *** two openly available datasets,extensive trials show that our proposed SADT performs much better than the state-ofthe-art semi-supervised medical segmentation *** only 10%of the labeled data for training,SADT was able to acquire a Dice score of 90.10%on the ACDC(Automatic Cardiac Diagnosis Challenge)dataset.